arXiv research

This note shows surfaces in stable 3D data are bounded by area and diameter.

Paper proves rigidity of initial data sets with boundary and capillary MOTS.

DreamFusion uses text-to-image diffusion models to create 3D images efficiently.

The paper proves a spacetime version of dihedral rigidity for cubes in 3D spacetime.

Establishes smooth Ricci flows from convex surfaces in 3D space.

Study on 3D spacetimes, focusing on vacuum data and energy bounds.

The paper proves energy theorems for specific initial data sets in 3D spacetime.

We propose a predictive neural network architecture that can be utilized to update reference velocity models as inputs to the full waveform inversion. Deep learning models are explored to augment velocity model building workflows during processing the 3D seismic volume in salt-prone environments. Specifically, a neural…

It is shown that 3D part of a spherically symmetric solution in conformal Weyl gravity interacting with Maxwell electrodynamics is a Yamabe flow as well. The Yamabe flow describes the transition from a horn of an initial wormhole to a 3D Euclidean space both filled with a radial electric field. It is supposed that such…

Determining the 3D structures of biological molecules is a key problem for both biology and medicine. Electron Cryomicroscopy (Cryo-EM) is a promising technique for structure estimation which relies heavily on computational methods to reconstruct 3D structures from 2D images. This paper introduces the challenging Cryo-…

The only known example of collapsed three-dimensional complete gradient steady Ricci solitons so far is the 3D cigar soliton $N^2\times \mathbb{R}$, the product of Hamilton's cigar soliton $N^2$ and the real line $\mathbb{R}$ with the product metric. R. Hamilton has conjectured that there should exist a family of colla…

The paper proves smoothness of mean curvature flow for generic initial data in 3D and 4D.

Solves Jang equation for hyperboloidal data, proving positive mass theorem.

Study shows generic surfaces avoid complex flow patterns.

Improved object segmentation and tracking in video using optical flow and initial state conditioning.

Brain tumor segmentation from Magnetic Resonance Images (MRIs) is an important task to measure tumor responses to treatments. However, automatic segmentation is very challenging. This paper presents an automatic brain tumor segmentation method based on a Normalized Gaussian Bayesian classification and a new 3D Fluid Ve…

When classifying point clouds, a large amount of time is devoted to the process of engineering a reliable set of features which are then passed to a classifier of choice. Generally, such features - usually derived from the 3D-covariance matrix - are computed using the surrounding neighborhood of points. While these fea…

Neural networks compress uninformative input directions, improving test error.

Geodesics spiral around Reeb orbits in 3D contact manifolds.

GTA improves transformer-based NVS models by encoding geometric structure.

The paper studies parallel spinor flows on 3D Cauchy hypersurfaces and provides initial data characterizations.

Paper develops a new method to analyze 3D tree-like objects.

Topology-GS improves 3D GS for better structural and feature integrity.

Selective relevance method improves motion explainability in 3D activity recognition models.

Understanding the three-dimensional (3D) structure of the genome is essential for elucidating vital biological processes and their links to human disease. To determine how the genome folds within the nucleus, chromosome conformation capture methods such as HiC have recently been employed. However, computational methods…

3D convolutional neural networks are difficult to train because they are parameter-expensive and data-hungry. To solve these problems we propose a simple technique for learning 3D convolutional kernels efficiently requiring less training data. We achieve this by factorizing the 3D kernel along the temporal dimension, r…

3D Convolutional Neural Networks (3D-CNN) have been used for object recognition based on the voxelized shape of an object. However, interpreting the decision making process of these 3D-CNNs is still an infeasible task. In this paper, we present a unique 3D-CNN based Gradient-weighted Class Activation Mapping method (3D…

Noise2Filter improves 3D tomography reconstruction efficiency and accuracy.

Transformer-M learns molecular data in 2D or 3D formats.

New method clusters multimodal data with consistency.

Deep learning models predict option prices from 3D tensor data.

The importance of training robust neural network grows as 3D data is increasingly utilized in deep learning for vision tasks in robotics, drone control, and autonomous driving. One commonly used 3D data type is 3D point clouds, which describe shape information. We examine the problem of creating robust models from the …

3D object classification and segmentation using deep neural networks has been extremely successful. As the problem of identifying 3D objects has many safety-critical applications, the neural networks have to be robust against adversarial changes to the input data set. There is a growing body of research on generating h…

This work generates synthetic 3D thermal facial data using 2D facial data and deep learning.

A novel deep learning architecture (XmasNet) based on convolutional neural networks was developed for the classification of prostate cancer lesions, using the 3D multiparametric MRI data provided by the PROSTATEx challenge. End-to-end training was performed for XmasNet, with data augmentation done through 3D rotation a…

GIBLy adds geometric priors to 3D segmentation models, improving performance with minimal overhead.

Robust deep neural networks estimate multi-dimensional functional data robustly.

Deep generative architectures provide a way to model not only images but also complex, 3-dimensional objects, such as point clouds. In this work, we present a novel method to obtain meaningful representations of 3D shapes that can be used for challenging tasks including 3D points generation, reconstruction, compression…

Study on subgroups' evolution in 3D Lie groups using mean curvature flow.

Improved 3D LiDAR data classification using product coefficients.

In this work we describe a novel deep reinforcement learning architecture that allows multiple actions to be selected at every time-step in an efficient manner. Multi-action policies allow complex behaviours to be learnt that would otherwise be hard to achieve when using single action selection techniques. We use both …

3D RadViz improves 3D data visualization of multidimensional datasets.

3D convolutional neural networks (3D-CNN) have been used for object recognition based on the voxelized shape of an object. In this paper, we present a 3D-CNN based method to learn distinct local geometric features of interest within an object. In this context, the voxelized representation may not be sufficient to captu…

Graph Neural Networks improve 3D object detection in LiDAR point clouds.

Deep learning within the context of point clouds has gained much research interest in recent years mostly due to the promising results that have been achieved on a number of challenging benchmarks, such as 3D shape recognition and scene semantic segmentation. In many realistic settings however, snapshots of the environ…

New benchmark for non-rigid 3D human shape retrieval.

3D object detection improved using energy-based models.

3D object recognition accuracy can be improved by learning the multi-scale spatial features from 3D spatial geometric representations of objects such as point clouds, 3D models, surfaces, and RGB-D data. Current deep learning approaches learn such features either using structured data representations (voxel grids and o…